WzY1924561588 commited on
Commit
3ee4a51
1 Parent(s): 212eaff

Training completed!

Browse files
README.md CHANGED
@@ -1,82 +1,82 @@
1
- ---
2
- license: apache-2.0
3
- base_model: distilbert-base-uncased
4
- tags:
5
- - generated_from_trainer
6
- datasets:
7
- - emotion
8
- metrics:
9
- - accuracy
10
- - f1
11
- model-index:
12
- - name: distilbert-base-uncased-finetuned-emotion
13
- results:
14
- - task:
15
- name: Text Classification
16
- type: text-classification
17
- dataset:
18
- name: emotion
19
- type: emotion
20
- config: split
21
- split: validation
22
- args: split
23
- metrics:
24
- - name: Accuracy
25
- type: accuracy
26
- value: 0.923
27
- - name: F1
28
- type: f1
29
- value: 0.9228871558865034
30
- ---
31
-
32
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
33
- should probably proofread and complete it, then remove this comment. -->
34
-
35
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wzy_study/huggingface/runs/p4tszd66)
36
- # distilbert-base-uncased-finetuned-emotion
37
-
38
- This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
39
- It achieves the following results on the evaluation set:
40
- - Loss: 0.2191
41
- - Accuracy: 0.923
42
- - F1: 0.9229
43
-
44
- ## Model description
45
-
46
- More information needed
47
-
48
- ## Intended uses & limitations
49
-
50
- More information needed
51
-
52
- ## Training and evaluation data
53
-
54
- More information needed
55
-
56
- ## Training procedure
57
-
58
- ### Training hyperparameters
59
-
60
- The following hyperparameters were used during training:
61
- - learning_rate: 2e-05
62
- - train_batch_size: 64
63
- - eval_batch_size: 64
64
- - seed: 42
65
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
- - lr_scheduler_type: linear
67
- - num_epochs: 2
68
-
69
- ### Training results
70
-
71
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
72
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
73
- | 0.8408 | 1.0 | 250 | 0.3211 | 0.9045 | 0.9031 |
74
- | 0.2539 | 2.0 | 500 | 0.2191 | 0.923 | 0.9229 |
75
-
76
-
77
- ### Framework versions
78
-
79
- - Transformers 4.42.3
80
- - Pytorch 2.1.0+cu118
81
- - Datasets 2.20.0
82
- - Tokenizers 0.19.1
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - emotion
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ model-index:
12
+ - name: distilbert-base-uncased-finetuned-emotion
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: emotion
19
+ type: emotion
20
+ config: split
21
+ split: validation
22
+ args: split
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.9205
27
+ - name: F1
28
+ type: f1
29
+ value: 0.9206794124018374
30
+ ---
31
+
32
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
33
+ should probably proofread and complete it, then remove this comment. -->
34
+
35
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wzy_study/huggingface/runs/ggpjqrrn)
36
+ # distilbert-base-uncased-finetuned-emotion
37
+
38
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
39
+ It achieves the following results on the evaluation set:
40
+ - Loss: 0.2168
41
+ - Accuracy: 0.9205
42
+ - F1: 0.9207
43
+
44
+ ## Model description
45
+
46
+ More information needed
47
+
48
+ ## Intended uses & limitations
49
+
50
+ More information needed
51
+
52
+ ## Training and evaluation data
53
+
54
+ More information needed
55
+
56
+ ## Training procedure
57
+
58
+ ### Training hyperparameters
59
+
60
+ The following hyperparameters were used during training:
61
+ - learning_rate: 2e-05
62
+ - train_batch_size: 64
63
+ - eval_batch_size: 64
64
+ - seed: 42
65
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
+ - lr_scheduler_type: linear
67
+ - num_epochs: 2
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
72
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
73
+ | 0.8052 | 1.0 | 250 | 0.3082 | 0.9105 | 0.9103 |
74
+ | 0.2458 | 2.0 | 500 | 0.2168 | 0.9205 | 0.9207 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.42.3
80
+ - Pytorch 2.1.2+cu121
81
+ - Datasets 2.20.0
82
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -1,41 +1,41 @@
1
- {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
- "architectures": [
5
- "DistilBertForSequenceClassification"
6
- ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
11
- "id2label": {
12
- "0": "LABEL_0",
13
- "1": "LABEL_1",
14
- "2": "LABEL_2",
15
- "3": "LABEL_3",
16
- "4": "LABEL_4",
17
- "5": "LABEL_5"
18
- },
19
- "initializer_range": 0.02,
20
- "label2id": {
21
- "LABEL_0": 0,
22
- "LABEL_1": 1,
23
- "LABEL_2": 2,
24
- "LABEL_3": 3,
25
- "LABEL_4": 4,
26
- "LABEL_5": 5
27
- },
28
- "max_position_embeddings": 512,
29
- "model_type": "distilbert",
30
- "n_heads": 12,
31
- "n_layers": 6,
32
- "pad_token_id": 0,
33
- "problem_type": "single_label_classification",
34
- "qa_dropout": 0.1,
35
- "seq_classif_dropout": 0.2,
36
- "sinusoidal_pos_embds": false,
37
- "tie_weights_": true,
38
- "torch_dtype": "float32",
39
- "transformers_version": "4.42.3",
40
- "vocab_size": 30522
41
- }
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": false,
37
+ "tie_weights_": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.42.3",
40
+ "vocab_size": 30522
41
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d5c31a5fa4a64e326e2564fd2c7157355019c869925bb1ff2331d7e4d9154d7
3
  size 267844872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295c5d199db477fea46aba44e30ded147aebf2f503e19306e5137bfd999b1fd1
3
  size 267844872
runs/Jul01_08-38-07_autodl-container-63564b9725-c95ebd5f/events.out.tfevents.1719794293.autodl-container-63564b9725-c95ebd5f.2250.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7cb68c69e427a842633a36bdc5e51ff1ca39402b876a9d5360f088b85bbcf6
3
+ size 6607
runs/Jul01_09-00-48_autodl-container-63564b9725-c95ebd5f/events.out.tfevents.1719795651.autodl-container-63564b9725-c95ebd5f.3078.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3d891a8227f62c4531ad702dcbab3e6e09822e1d1b46d8770c369ea290581e
3
+ size 6607
special_tokens_map.json CHANGED
@@ -1,7 +1,7 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json CHANGED
@@ -1,55 +1,55 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
- "mask_token": "[MASK]",
48
- "model_max_length": 512,
49
- "pad_token": "[PAD]",
50
- "sep_token": "[SEP]",
51
- "strip_accents": null,
52
- "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
- "unk_token": "[UNK]"
55
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:115b9aed9f653526ae6ff4129082de2c6b5a0a1f641182cc00ee40062d9ed20c
3
- size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a96d6cfa4d6c39f6153b03cbea0d2206481a12c69f3649e2394c631722007a
3
+ size 5240